claims-fact-check
Pass
Audited by Gen Agent Trust Hub on Oct 25, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local Python utility,
scripts/claims_scan.py, to extract claims and verify date/weekday consistency. This is a standard functional component of the skill's logic. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted data from web pages, uploaded files, and user-provided text. It includes specific defensive instructions requiring the agent to treat fetched content as data rather than instructions, and to report any detected injection attempts.
- [EXTERNAL_DOWNLOADS]: The skill references and fetches content from reputable business and financial sources (such as the National Stock Exchange of India and BusinessWire) as part of its fact-checking workflow.
- [DATA_EXPOSURE_EXFILTRATION]: The skill includes a dedicated personal data check for images, instructing the agent to identify and suggest redaction for sensitive information like email addresses, file paths, and internal account IDs.
Audit Metadata